Perplexity Ask OpenRouter
@elct9620
Perplexity Ask OpenRouter について
The Perplexity Ask MCP Server use OpenRouter
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"perplexity-ask-openrouter": {
"command": "docker",
"args": [
"run",
"-p",
"3000:3000",
"\\"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Perplexity Ask OpenRouter?
Perplexity Ask OpenRouter is a Model Context Protocol (MCP) server that connects Perplexity’s models to the OpenRouter API, enabling their use with any MCP-compatible client. It is designed for developers who want to access Perplexity’s models (Sonar, Sonar Deep Research, Sonar Reasoning) through OpenRouter.
How to use Perplexity Ask OpenRouter?
The easiest way is to run the prebuilt Docker image with your OpenRouter API key and optionally set model defaults via environment variables (ASK_MODEL, RESEARCH_MODEL, REASON_MODEL). The server exposes SSE and Streamable HTTP endpoints for MCP clients, and disable flags (DISABLE_ASK, DISABLE_RESEARCH, DISABLE_REASON) let you turn off specific tools.
Key features of Perplexity Ask OpenRouter
- Full Model Context Protocol (MCP) implementation
- Three Perplexity models via OpenRouter: ask, research, reason
- Server-Sent Events (SSE) transport support
- Streamable HTTP transport implementation
- Docker containerization for easy deployment
- Environment variables to configure models and ports
Use cases of Perplexity Ask OpenRouter
- Ask general-purpose questions using the Sonar model via any MCP client
- Perform deep research on complex topics with Sonar Deep Research
- Solve reasoning tasks requiring logical deduction using Sonar Reasoning
- Integrate Perplexity’s conversational AI into custom MCP-powered tools
FAQ from Perplexity Ask OpenRouter
What dependencies does the server require?
An OpenRouter API key set via the OPENROUTER_API_KEY environment variable is required. No other external services are needed if using the default Docker image.
What transport protocols are supported?
The server supports both SSE (via /sse and /messages endpoints) and Streamable HTTP (via /mcp endpoint). Both can be used by any MCP-compatible client.
Is there a known limitation on request volume or rate?
The README does not specify rate limits. All requests are routed through OpenRouter and subject to OpenRouter’s own limits.
Where does data (prompts, responses) live?
In transit between the MCP client, the server, and OpenRouter. No persistent storage is mentioned in the README.
How is authentication handled?
The server authenticates with OpenRouter using the OPENROUTER_API_KEY environment variable. No additional authentication is required for MCP clients.
「AI とエージェント」の他のコンテンツ
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
meGPT - upload an author's content into an LLM
adriancoCode to process many kinds of content by an author into an MCP server
MCP Claude Code
SDGLBLMCP implementation of Claude Code capabilities and more
Shell and Coding agent for Claude and other mcp clients
rusiaamanShell and coding agent on mcp clients
コメント